Segmentation-free Keyword Spotting for Bangla Handwritten Documents

In this paper, a segmentation-free keyword spotting method is proposed for Bangla handwritten documents. In order to tolerate large variations in handwritten scenarios, we extracted keypoints based on SIFT keypoint detector, and the end and intersection points found by morphological operations. Heat Kernel signature (HKS) is used to present the local characteristics of detected keypoints. Instead of using the same size of patch for all the keypoints, we apply a method dynamically deciding the patch size. Furthermore, our spotting method reduces the scope of searching on the document by only considering the candidate local zones with similar candidate keypoints, and does not need pre-processing steps. From the experiment on Bangla handwritten text we obtained encouraging results.